no code implementations • 23 Feb 2023 • El Mahdi Chayti, Nikita Doikov, Martin Jaggi
Our helper framework offers the algorithm designer high flexibility for constructing and analyzing the stochastic Cubic Newton methods, allowing arbitrary size batches, and the use of noisy and possibly biased estimates of the gradients and Hessians, incorporating both the variance reduction and the lazy Hessian updates.
no code implementations • 1 Dec 2022 • Nikita Doikov, El Mahdi Chayti, Martin Jaggi
This provably improves the total arithmetical complexity of second-order algorithms by a factor $\sqrt{d}$.
1 code implementation • 1 Jun 2022 • El Mahdi Chayti, Sai Praneeth Karimireddy
We investigate the fundamental optimization question of minimizing a target function $f$, whose gradients are expensive to compute or have limited availability, given access to some auxiliary side function $h$ whose gradients are cheap or more available.
1 code implementation • 10 Nov 2021 • El Mahdi Chayti, Sai Praneeth Karimireddy, Sebastian U. Stich, Nicolas Flammarion, Martin Jaggi
Collaborative training can improve the accuracy of a model for a user by trading off the model's bias (introduced by using data from other users who are potentially different) against its variance (due to the limited amount of data on any single user).